Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs following the word "to"

    oai_token-act-pair · gpt-3.5-turbo

    infinitive forms of verbs, particularly those indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    views
    -0.69
    ciating
    -0.69
    interstitial
    -0.68
    lus
    -0.67
    comments
    -0.66
    Tip
    -0.65
     Tips
    -0.64
    angered
    -0.64
     reminders
    -0.63
     Warning
    -0.61
    POSITIVE LOGITS
     accomplish
    1.42
     achieve
    1.16
     do
    1.13
     automate
    1.07
     implement
    1.01
     undertake
    0.95
     execute
    0.93
     succeed
    0.93
     proceed
    0.93
     feas
    0.92
    Act Density 0.279%

    No Known Activations